161–170 of 322 posts
I'm a software developer from way back, using tools and languages that coding agents are far less familiar with. So when I use an agent to write code, it's in languages I'm less familiar with, and often using libraries I know nothing about. All to say, my part of the process often ends up being: 1. "Here's what I'm looking for, in detail" 2. "That's not right. Here's one way it's not right, and a specific example. Pl…
For some reason pro-ai blog posts feel like paid ads, I might be wrong.
> Claude's attention doesn't distinguish between "instructions I'm writing" and "instructions I'm following" -- they're both just tokens in context.
It takes a little human help in the first iterations but after a while it will start to iterate and improve unsupervised.
I have had some success with /goal for long tasks that can be set up in a way that the agent can do good work for an extended period of time. A lot of tasks aren't amenable to that, and the ones that are still need a lot of care to be set up correctly. The default vibe coded codebase won't be. I've come to think of the activity of choosing the right technology, the right architecture, the right testing setup, the rig…
https://code.claude.com/docs/en/goal#how-evaluation-works
> /goal is a wrapper around a session-scoped prompt-based Stop hook. Each time Claude finishes a turn, the condition and the conversation so far are sent to your configured small fast model, which defaults to Haiku. The model returns a yes-or-no decision and a short reason. A “no” tells Claude to keep working and includes the reason as guidance for the next turn. A “yes” clears the goal and records an achieved entry in the transcript.
> The evaluator runs on whichever provider your session is configured for. It does not call tools, so it can only judge what Claude has already surfaced in the conversation.
Apparently, it uses Haiku (by default) to evaluate every turn to determine if the goal has been achieved. However, it only relies on the transcript itself (including the reasoning of the main model). It can't independently verify if the goal has been achieved. So, if the main model thinks the goal is or isn't done, how often does Haiku disagree (in a productive way)? That's not clear to me.
For some reason pro-ai blog posts feel like paid ads, I might be wrong.
Who cares what Cherny thinks? He is selling his product, and he will probably cash out soon enough while his credibility is as high as it is.
What does any of that mean in practice? it's just rambling about abstract concepts that seem to be designed to hint at a bigger picture, when it's just getting AI to write code for you. Is this where it's going? Having to mystify our roles so it seems like we're still the thought leaders when actually we're just becoming pseudo-teachers that try and herd our group of AI idiots to the right conclusion for us so we don…
The speed of improvement on these models has been incredible and has outpaced the learning speed of humans and put many experts into these Shamanistic roles.
I think the operative means of addressing this is to recognize that we can only learn so quickly, but we are still called to improve our knowledge and understanding to a higher level. Since the improvement of these models is neither logorithmic, nor exponential, we currently occupy a space in time in which the models are currently smarter on average than we are as a collective whole.
For some reason pro-ai blog posts feel like paid ads, I might be wrong.
> the right fix is not "handle every malformed case." ... [LLMs] will still attempt to handle now impossible errors. This is the number one code smell from LLMs and I don't know why they are so obsessed with it. In python, it often comes as `hasattr` checks on types that are defined to have that attribute, in a code base that is fully type-checked. Why do they do that? Is it from pre-training or re-enforcement? If th…
What does any of that mean in practice? it's just rambling about abstract concepts that seem to be designed to hint at a bigger picture, when it's just getting AI to write code for you. Is this where it's going? Having to mystify our roles so it seems like we're still the thought leaders when actually we're just becoming pseudo-teachers that try and herd our group of AI idiots to the right conclusion for us so we don…
My own feeling is that it is totally OK to simply route around these people.
It's fascinating how many of the "keep your identity small" folks in the YC/HN sphere have lost any sense of perspective at the first sign of a technology that wanders into the philosophical realm. AI-oriented identities are everywhere.